wangzfsh/upernet-convnext-base-AIData-198

upernet-convnext-base-AIData

This model is a fine-tuned version of openmmlab/upernet-convnext-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0005
• Mean Iou: 0.8401
• Mean Accuracy: 0.8941
• Overall Accuracy: 0.9999
• Per Category Iou: [0.9999000813657232, 0.6803966437833715]
• Per Category Accuracy: [0.9999571923167959, 0.7883340698188246]

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.0005	11.7647	200	0.0005	0.8172	0.8557	0.9999	[0.9998894717752407, 0.6346078044934963]	[0.9999673278406743, 0.7114449845338047]
0.0005	23.5294	400	0.0005	0.8456	0.9072	0.9999	[0.9999018691950949, 0.691297824456114]	[0.9999519456926707, 0.8144056562085726]
0.0005	35.2941	600	0.0005	0.8413	0.8950	0.9999	[0.999900915960996, 0.6827033218785796]	[0.9999575500411682, 0.7901016349977905]
0.0005	47.0588	800	0.0005	0.8401	0.8941	0.9999	[0.9999000813657232, 0.6803966437833715]	[0.9999571923167959, 0.7883340698188246]

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3